1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
* Copyright (c) 2020 Mellanox Technologies. All rights reserved.
*/
#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>
#include <rdma/lag.h>
static struct sk_buff *rdma_build_skb(struct ib_device *device,
struct net_device *netdev,
struct rdma_ah_attr *ah_attr,
gfp_t flags)
{
struct ipv6hdr *ip6h;
struct sk_buff *skb;
struct ethhdr *eth;
struct iphdr *iph;
struct udphdr *uh;
u8 smac[ETH_ALEN];
bool is_ipv4;
int hdr_len;
is_ipv4 = ipv6_addr_v4mapped((struct in6_addr *)ah_attr->grh.dgid.raw);
hdr_len = ETH_HLEN + sizeof(struct udphdr) + LL_RESERVED_SPACE(netdev);
hdr_len += is_ipv4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr);
skb = alloc_skb(hdr_len, flags);
if (!skb)
return NULL;
skb->dev = netdev;
skb_reserve(skb, hdr_len);
skb_push(skb, sizeof(struct udphdr));
skb_reset_transport_header(skb);
uh = udp_hdr(skb);
uh->source = htons(0xC000);
uh->dest = htons(ROCE_V2_UDP_DPORT);
uh->len = htons(sizeof(struct udphdr));
if (is_ipv4) {
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->frag_off = 0;
iph->version = 4;
iph->protocol = IPPROTO_UDP;
iph->ihl = 0x5;
iph->tot_len = htons(sizeof(struct udphdr) + sizeof(struct
iphdr));
memcpy(&iph->saddr, ah_attr->grh.sgid_attr->gid.raw + 12,
sizeof(struct in_addr));
memcpy(&iph->daddr, ah_attr->grh.dgid.raw + 12,
sizeof(struct in_addr));
} else {
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ip6h = ipv6_hdr(skb);
ip6h->version = 6;
ip6h->nexthdr = IPPROTO_UDP;
memcpy(&ip6h->flow_lbl, &ah_attr->grh.flow_label,
sizeof(*ip6h->flow_lbl));
memcpy(&ip6h->saddr, ah_attr->grh.sgid_attr->gid.raw,
sizeof(struct in6_addr));
memcpy(&ip6h->daddr, ah_attr->grh.dgid.raw,
sizeof(struct in6_addr));
}
skb_push(skb, sizeof(struct ethhdr));
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
skb->protocol = eth->h_proto = htons(is_ipv4 ? ETH_P_IP : ETH_P_IPV6);
rdma_read_gid_l2_fields(ah_attr->grh.sgid_attr, NULL, smac);
memcpy(eth->h_source, smac, ETH_ALEN);
memcpy(eth->h_dest, ah_attr->roce.dmac, ETH_ALEN);
return skb;
}
static struct net_device *rdma_get_xmit_slave_udp(struct ib_device *device,
struct net_device *master,
struct rdma_ah_attr *ah_attr,
gfp_t flags)
{
struct net_device *slave;
struct sk_buff *skb;
skb = rdma_build_skb(device, master, ah_attr, flags);
if (!skb)
return ERR_PTR(-ENOMEM);
rcu_read_lock();
slave = netdev_get_xmit_slave(master, skb,
!!(device->lag_flags &
RDMA_LAG_FLAGS_HASH_ALL_SLAVES));
if (slave)
dev_hold(slave);
rcu_read_unlock();
kfree_skb(skb);
return slave;
}
void rdma_lag_put_ah_roce_slave(struct net_device *xmit_slave)
{
if (xmit_slave)
dev_put(xmit_slave);
}
struct net_device *rdma_lag_get_ah_roce_slave(struct ib_device *device,
struct rdma_ah_attr *ah_attr,
gfp_t flags)
{
struct net_device *slave = NULL;
struct net_device *master;
if (!(ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE &&
ah_attr->grh.sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP))
return NULL;
rcu_read_lock();
master = rdma_read_gid_attr_ndev_rcu(ah_attr->grh.sgid_attr);
if (IS_ERR(master)) {
rcu_read_unlock();
return master;
}
dev_hold(master);
rcu_read_unlock();
if (!netif_is_bond_master(master))
goto put;
slave = rdma_get_xmit_slave_udp(device, master, ah_attr, flags);
put:
dev_put(master);
return slave;
}
|